INFANT: a modular approach to natural language processing

ABSTRACT

The INFANT System is a working natural language processing system that approaches language analysis through the integration of a large number of interdependent procedural modules. By themselves the modules perform specific, predictable, and rather mundane tasks; taken together, they make up an understanding system whose 'beliefs' and responses are varied and unpredictable. Thus a type of emergent behavior is demonstrated by the system. This paper describes the overall modular design of INFANT, and illustrates through sample conversations some of its capabilities and deficiencies.

REFERENCES

• 1: Zenon W. Pylyshyn, Computation and cognition: toward a foundation for cognitive science, Massachusetts Institute of Technology, Cambridge, MA, 1984
• 2: Jerry A. Fodor , Zenon W. Pylyshyn, Connectionism and cognitive architecture: a critical analysis, Connections and symbols, MIT Press, Cambridge, MA, 1988
• 3: Douglas B. Lenat , R. V. Guha , Karen Pittman , Dexter Pratt , Mary Shepherd, Cyc: toward programs with common sense, Communications of the ACM, v.33 n.8, p.30-49, Aug. 1990 [doi>10.1145/79173.79176]
• 4: Marvin Minsky, The society of mind, Simon & Schuster, Inc., New York, NY, 1986
• 5: David Marr, AI: a personal view, The foundation of artificial intelligence---a sourcebook, Cambridge University Press, New York, NY, 1990
• 6: Paul Buchheit, An Informational Network for a Natural Talking System, Proceedings of the The First Great Lakes Computer Science Conference on Computing in the 90's, p.84-90, October 18-20, 1989
• 7: Paul Joseph Buchheit, Infant: a connectionist-like knowledge base and natural language processing system, University of Illinois at Chicago, Chicago, IL, 1992
• 8: Buchheit, Paul and Conant, Roger (1992). 'lnferencing and Learning in the INFANT System.' Proceedings of the 4th Midwest Artificial Intelligence and Cognitive Science Society Conference (sponsored by Southern Illinois University), Utica IL, May 3-4, pp. 37-41.
• 9: van Dijk, Teun A. and Kintsch, Walter (1983). Strategies of Discourse Processing (Academic Press, New York).
• 10: Wilks, Yorick (1976). 'Parsing English II.' In Chamiak, Eugene and Wilks, Yorick, Comt~arional Semantics (North-Holland, Amsterdam).
• 11: Buchheit, Paul and Con,ant, Roger (1991). 'KnoMedge Representation and Inference Control in a Natural Language System.' Proceedings of the Third International Conference on Software Engineering and Knowledge Eng~ering, Knowledge Systems Institute, Skokie, IL, 6/27/91, pp. 52-57.
• 12: Schank, R., Goldman, N., Rieger, C., and Riesbeck, C. 1973. "MARGIE: Memory, Analysis, Response Generation, and Inference on English." //CA/3, 255-61.

INDEX TERMS

Primary Classification:
  I. Computing Methodologies
  I.2 ARTIFICIAL INTELLIGENCE
      I.2.7 Natural Language Processing
          Subjects: Language parsing and understanding

Additional Classification:
  I. Computing Methodologies
  I.2 ARTIFICIAL INTELLIGENCE
      I.2.0 General
          Subjects: Cognitive simulation
      I.2.3 Deduction and Theorem Proving
          Subjects: Deduction (e.g., natural, rule-based)
      I.2.6 Learning
          Subjects: Connectionism and neural nets

General Terms:
Algorithms, Languages, Theory